© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25242
    Prev
    Next
    INDEX
    Explanations

    programming/technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бÑĢа
    -0.28
    etc
    -0.25
    ierce
    -0.25
     froze
    -0.24
    _clicked
    -0.24
    .currentState
    -0.23
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.23
    Ò·
    -0.23
    ather
    -0.23
    çļĦçī¹çĤ¹
    -0.23
    POSITIVE LOGITS
    -fat
    0.26
     knowledge
    0.26
     concert
    0.26
    `:
    0.25
    aida
    0.25
    çļĦçŁ¥è¯Ĩ
    0.25
    rys
    0.24
    utoff
    0.24
    tot
    0.24
    iens
    0.24
    Activations Density 0.061%

    No Known Activations